12,808 Hits in 5.2 sec

Secure Deep Learning Engineering: A Software Quality Assurance Perspective [article]

Lei Ma, Felix Juefei-Xu, Minhui Xue, Qiang Hu, Sen Chen, Bo Li, Yang Liu, Jianjun Zhao, Jianxiong Yin, Simon See
2018 arXiv   pre-print
In this paper, we perform a large-scale study and construct a paper repository of 223 relevant works to the quality assurance, security, and interpretation of deep learning.  ...  We, from a software quality assurance perspective, pinpoint challenges and future opportunities towards universal secure deep learning engineering.  ...  We define Secure Deep Learning Engineering (SDLE) as an engineering discipline of deep learning software production, through a systematic application of knowledge, methodology, practice on deep learning  ... 
arXiv:1810.04538v1 fatcat:fbxdxvw55zc7vbkpjm6bpknlby

Pros and Cons of Fault Injection Approaches for the Reliability Assessment of Deep Neural Networks

Annachiara Ruospo, Lucas Matana Luza, Alberto Bosio, Marcello Traiola, Luigi Dilillo, Ernesto Sanchez
2021 2021 IEEE 22nd Latin American Test Symposium (LATS)  
For this reason, the research community has shown a growing interest in understanding the robustness of artificial computing models to hardware faults.  ...  This work classifies and analyses the principal reliability assessment methodologies based on Fault Injection at different abstraction levels and with different procedures.  ...  The authors in [17] present a resilience analysis framework to study transient hardware errors in deep learning accelerators leveraging on high-level design information obtained from architectural descriptions  ... 
doi:10.1109/lats53581.2021.9651807 fatcat:4s2nwlkwyfgyholbu7j7pvxope

Editorial: State-of-the-Art Technology and Applications in Crop Phenomics

Wanneng Yang, John H. Doonan, Malcolm J. Hawkesford, Tony Pridmore, Ji Zhou
2021 Frontiers in Plant Science  
costs in software and hardware systems.  ...  The integration of artificial intelligence (AI) driven techniques (e.g., deep learning and machine learning), computer vision, and big-data analytics, and their optimization for the life sciences, has  ...  costs in software and hardware systems.  ... 
doi:10.3389/fpls.2021.767324 pmid:34675958 pmcid:PMC8524054 fatcat:m5zoaazvurbytazqpuslmaxney

Quality assurance methodologies for automated driving

Franz Wotawa, Bernhard Peischl, Florian Klück, Mihai Nica
2018 e & i Elektrotechnik und Informationstechnik  
This includes the question of how to assure that artificial intelligence and machine learning based systems fulfill safety criticality requirements under all potential conditions and situations that may  ...  For safety critical systems like cars, trains, or airplanes quality assurance methods and techniques are crucial for preventing situations that may harm people.  ...  The financial support by the Austrian Federal Ministry for Digital and Economic Affairs and the National Foundation for Research, Technology and Development is gratefully acknowledged.  ... 
doi:10.1007/s00502-018-0630-7 fatcat:5jm7xvhhcjaw5jz3qbha4ob3ry

FeCaffe: FPGA-enabled Caffe with OpenCL for Deep Learning Training and Inference on Intel Stratix 10 [article]

Ke He, Bo Liu, Yu Zhang, Andrew Ling, Dian Gu
2019 arXiv   pre-print
FPGA-enabled Caffe, a hierarchical software and hardware design methodology based on the Caffe to enable FPGA to support mainline deep learning development features, e.g. training and inference with Caffe  ...  reusability for deep learning development.  ...  , and introduce the hierarchical hardware and software design methodology accordingly in details.  ... 
arXiv:1911.08905v1 fatcat:k727mudp3neutbj7nnwbzvfk6a

Distributed Intelligence on the Edge-to-Cloud Continuum: A Systematic Literature Review

Daniel Rosendo, Alexandru Costan, Patrick Valduriez, Gabriel Antoniu
2022 Journal of Parallel and Distributed Computing  
review aims at providing a comprehensive vision of the main state-of-the-art libraries and frameworks for machine learning and data analytics available today.  ...  The large scale and optimized deployment of learning-based workflows across the Edge-to-Cloud Continuum requires extensive and reproducible experimental analysis of the application execution on representative  ...  Acknowledgments This work was funded by Inria through the HPC-BigData Inria Challenge (IPL) and by French ANR OverFlow project (ANR-15-CE25-0003).  ... 
doi:10.1016/j.jpdc.2022.04.004 fatcat:mopdegh4vrgt5k47vrmc7xum24

Security Analysis and Enhancement of Model Compressed Deep Learning Systems under Adversarial Attacks [article]

Qi Liu, Tao Liu, Zihao Liu, Yanzhi Wang, Yier Jin, Wujie Wen
2018 arXiv   pre-print
We then conduct a comprehensive robustness and vulnerability analysis of deep compressed DNN models under derived adversarial attacks.  ...  For example, the emerging adversarial attacks indicate that even very small and often imperceptible adversarial input perturbations can easily mislead the cognitive function of deep learning systems (DLS  ...  A full MNIST database is adopted as our benchmark for a comprehensive analysis of attacking effectiveness in deep compressed/non-compressed deep learning systems. A.  ... 
arXiv:1802.05193v2 fatcat:dp3n32efgzfcpeyllv5rt3ot5q

Considerations Related to the Added Values Achieved in the VccSSe Comenius 2.1 European Project

Gabriel Gorghiu, Adina Elena Glava, Laura Monica Gorghiu, Cătălin Cosmin Glava
2011 Procedia - Social and Behavioral Sciences  
The main aim of the guidance was to make clear the teacher training requirements and to assure a general understanding among all trainers, tutors and partners.  ...  Faceto-face training sessions have been accompanied by specific guidance interventions, but also the platform used for on-line training offered the possibility to produce a real interaction tutor -trainer  ...  of EU's programmes in the fields of education, culture and audiovisual, through the project mentioned above, is gratefully acknowledged.  ... 
doi:10.1016/j.sbspro.2011.10.222 fatcat:cdgtcele6nb4xp3ylwox2onzny

Fine-Grained Energy and Performance Profiling framework for Deep Convolutional Neural Networks [article]

Crefeda Faviola Rodrigues, Graham Riley, Mikel Lujan
2018 arXiv   pre-print
There is a huge demand for on-device execution of deep learning algorithms on mobile and embedded platforms. These devices present constraints on the application due to limited resources and power.  ...  We integrate ARM's Streamline Performance Analyser with standard deep learning frameworks such as Caffe and CuDNNv5, to study the execution behaviour of current deep learning models at a fine-grained level  ...  However, these studies are often adhoc to study a limited set of deep learning models and platform-to-platform comparisons.  ... 
arXiv:1803.11151v2 fatcat:k3h4gnnbdvfk7beac6nhlmreem

Benchmarking TPU, GPU, and CPU Platforms for Deep Learning [article]

Yu Emma Wang, Gu-Yeon Wei, David Brooks
2019 arXiv   pre-print
To systematically benchmark deep learning platforms, we introduce ParaDnn, a parameterized benchmark suite for deep learning that generates end-to-end models for fully connected (FC), convolutional (CNN  ...  We also provide a thorough comparison of the platforms and find that each has unique strengths for some types of models.  ...  CONCLUSION This paper provides a comprehensive benchmarking analysis of deep neural network training hardware and software, and valuable lessons learned for future system designs.  ... 
arXiv:1907.10701v4 fatcat:s5br43qnqjb2xnht6ulvh45gkm

Tutorial: Open-Source EDA and Machine Learning for IC Design: A Live Update

Abdelrahman Hosny, Andrew B. Kahng
2020 2020 33rd International Conference on VLSI Design and 2020 19th International Conference on Embedded Systems (VLSID)  
start for design tool and methodology innovation.  ...  In particular, the tutorial will make a deep dive into The OpenROAD Project , which brings new open-source tools and machine learning into a "no human in the loop" RTL-to-GDS  ...  His research interests include hardware and software optimizations for machine/deep learning and approximate computing.  ... 
doi:10.1109/vlsid49098.2020.00016 dblp:conf/vlsid/HosnyK20 fatcat:gsvvnrgbr5dpdjwkkx63jnf2f4

2019 Index IEEE Transactions on Learning Technologies Vol. 12

2020 IEEE Transactions on Learning Technologies  
., +, TLT April-June 2019 148-157 Inquiry-Based Learning With RoboGen: An Open-Source Software and Hardware Platform for Robotics and Artificial Intelligence.  ...  -March 2019 98-111 Educational robots Inquiry-Based Learning With RoboGen: An Open-Source Software and Hardware Platform for Robotics and Artificial Intelligence.  ... 
doi:10.1109/tlt.2019.2961548 fatcat:vgjghhxvo5fhzalkovcjhvewqa

Methodological Aspects of the Use of Software in the Teaching of Engineering Disciplines: Tasks, Problems and Prospects

Irina K. Romanova, Y.I. Dimitrienko, E.N. Grigorieva
2020 ITM Web of Conferences  
The analysis of needs in the formation of new competencies based on the results of a survey of graduate students of BMSTU, and the views of employers, which showed the closeness of the representations  ...  These computer technologies have taken the project approach to learning to a new stage.  ...  Such a unifying program can serve, for example, the theme "Software and hardware systems for simulation and training for facility management".  ... 
doi:10.1051/itmconf/20203504020 fatcat:djg6dacg7rdnrm6gxipa5vripa

The review of heterogeneous design frameworks/Platforms for digital systems embedded in FPGAs and SoCs

Abdelhakim Alali, Hasna Elmaaradi, Mohammed Khaldoun, Mohamed Sadik
2021 Indonesian Journal of Electrical Engineering and Informatics (IJEEI)  
We will analyze several aspects constituting the architecture and the structure of the platforms to make a comparative study of the hardware and software design flows of digital systems.  ...  This paper illustrates some of them and presents a comparative study between them.  ...  It allows to development of solutions for deep learning via different abstractions and the export of graphs to other tools. As a result, [41] the deployment of ML applications becomes easier.  ... 
doi:10.52549/ijeei.v9i4.3243 fatcat:k76nmwodi5cfxk4c4hk3nojc7e


Yazid Abdullsameea Saif, Yusri Yusof, Maznah lliyas Ahmed, Zohaib khan Pathan, Kamran Latif, Aini Zuhra Abdul Kadir
The contribution of this study is to build a structure in the computer vision method with a convolution neural network that predicts the classification of the feature for better accuracy and emphasizes  ...  The framework depends on the new technique of Open CV, which includes two parts: an intelligent selection of work-piece capturing the image for a particular inspection of the planar interfaces such as  ...  Education and Scientific Research of Yemen for their sponsor.  ... 
doi:10.32890/jtom2020.15.2.5 fatcat:fwktewixsbdxvf3k4riqrbauzi
« Previous Showing results 1 — 15 out of 12,808 results